© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90318
    Prev
    Next
    INDEX
    Explanations

    code punctuation and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </b>
    -1.58
    </h1>
    -1.41
     For
    -1.36
     Even
    -1.33
    vel
    -1.24
     sosial
    -1.24
    Сю
    -1.23
     As
    -1.23
    ’:
    -1.20
    se
    -1.17
    POSITIVE LOGITS
     séjours
    1.41
     لأنه
    1.38
    deuse
    1.38
     seguras
    1.38
    <bos>
    1.38
     utilizadas
    1.33
     zowel
    1.32
     diamètre
    1.28
     Thủ
    1.28
     Estructura
    1.27
    Activations Density 0.046%

    No Known Activations